检索结果-内蒙古大学图书馆

IEEE Symposium on Adaptive Dynamic Programming and Reinforcement learning, (ADPRL)

作者： Alexander Hans Siegmund Duell Steffen Udluft Neuroinformatics and Cognitive Robotics Laboratory Ilmenau University of Technology Ilmenau Germany Machine Learning Group Berlin Institute of Technology Berlin Germany Intelligent Systems and Control Siemens AG Munich Germany

With the development of data-efficient reinforcement learning (RL) methods, a promising data-driven solution for optimal control of complex technical systems has become available. For the application of RL to a technical system, it is usually required to evaluate a policy before actually applying it to ensure it operates the system safely and within required performance bounds. In benchmark applications one can use the system dynamics directly to measure the policy quality. In real applications, however, this might be too expensive or even impossible. Being unable to evaluate the policy without using the actual system hinders the application of RL to autonomous controllers. As a first step toward agent self-assessment, we deal with discrete MDPs in this paper. We propose to use the value function along with its uncertainty to assess a policy's quality and show that, when dealing with an MDP estimated from observations, the value function itself can be misleading. We address this problem by determining the value function's uncertainty through uncertainty propagation and evaluate the approach using a number of benchmark applications.

关键词： Uncertainty Equations Markov processes Benchmark testing Approximation algorithms machine learning Histograms

来源：评论

学校读者我要写书评

暂无评论

Early Identification of Peer-to-Peer Traffic

Early Identification of Peer-to-Peer Traffic

引用

IEEE International Conference on Communications (ICC)

作者： Bela Hullar Sandor Laki Andras Gyorgy Department of Physics of Complex Systems Eötvös Lonránd University Budapest Hungary Department of Information Systems Eötvös Lonránd University Budapest Hungary Machine Learning Research Group MTA SZTAKI Institute of Computer Science and Control Budapest Hungary

To manage and monitor their networks in a proper way, network operators are often interested in identifying the applications generating the traffic traveling through their networks, and doing it as fast (i.e., from as few packets) as possible. State-of-the-art packet-based traffic classification methods are either based on the costly inspection of the payload of several packets of each flow or on basic flow statistics that do not take into account the packet content. In this paper we consider the intermediate approach of analyzing only the first few bytes of the first (or first few) packets of each flow. We propose automatic, machine-learning-based methods achieving remarkably good early classification performance on real traffic traces generated from a diverse set of applications (including several versions of P2P TV and file sharing), while requiring only limited computational and memory resources.

关键词： Protocols Payloads Markov processes Training Wireless LAN Radio frequency Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Bayesian mixed-effects inference on classification performance in hierarchical data sets

The Journal of Machine Learning Research

引用

The Journal of machine learning research 2012年第1期13卷

作者： Kay H. Brodersen Christoph Mathys Justin R. Chumbley Jean Daunizeau Cheng Soon Ong Joachim M. Buhmann Klaas E. Stephan Machine Learning Lab. Dept. of Comp. Sci. ETH Zurich Switzerland and Lab. for Social and Neural Systems Res. Dept. of Economics Univ. of Zurich Zurich Switzerland and Translational Neuromodeling Unit Inst. for Biomed. Eng. ETH Zurich and Univ. of Zurich Zurich Switzerland Laboratory for Social and Neural Systems Research Department of Economics University of Zurich Zurich Switzerland and Translational Neuromodeling Unit Institute for Biomedical Engineering ETH Zurich & University of Zurich Zurich Switzerland Laboratory for Social and Neural Systems Research Department of Economics University of Zurich Zurich Switzerland Machine Learning Laboratory Department of Computer Science ETH Zurich Zurich Switzerland Lab. for Social and Neural Sys. Res. Dept. of Economics Univ. of Zurich Switzerland Wellcome Trust Centre for Neuroimaging Univ. College London London United Kingdom and Translational Neuromodeling Unit Inst. for Biomedical Eng. ETH Zurich and Univ. of Zurich Zurich Switzerland

Classification algorithms are frequently used on data with a natural hierarchical structure. For instance, classifiers are often trained and tested on trial-wise measurements, separately for each subject within a group. One important question is how classification outcomes observed in individual subjects can be generalized to the population from which the group was sampled. To address this question, this paper introduces novel statistical models that are guided by three desiderata. First, all models explicitly respect the hierarchical nature of the data, that is, they are mixed-effects models that simultaneously account for within-subjects (fixed-effects) and across-subjects (random-effects) variance components. Second, maximum-likelihood estimation is replaced by full Bayesian inference in order to enable natural regularization of the estimation problem and to afford conclusions in terms of posterior probability statements. Third, inference on classification accuracy is complemented by inference on the balanced accuracy, which avoids inflated accuracy estimates for imbalanced data sets. We introduce hierarchical models that satisfy these criteria and demonstrate their advantages over conventional methods usingMCMC implementations for model inversion and model selection on both synthetic and empirical data. We envisage that our approach will improve the sensitivity and validity of statistical inference in future hierarchical classification studies.

关键词： Bayesian inference balanced accuracy beta-binomial group studies normal-binomial

来源：评论

学校读者我要写书评

暂无评论

Correlation transmission of spiking neurons is boosted by synchronous input

引用

BMC Neuroscience 2011年第1期12卷 1-2页

作者： Matthias Schultze-Kraft Markus Diesmann Moritz Helias Sonja Grün Machine Learning Group Berlin Institute of Technology Berlin Germany Laboratory for Computational Neurophysics RIKEN Brain Science Institute Wako City Japan Brain and Neural Systems Team RIKEN Computational Science Research Program Wako City Japan Institute of Neuroscience and Medicine (INM-6) Computational and Systems Neuroscience Research Center Jülich Germany Laboratory for Statistical Neuroscience RIKEN Brain Science Institute Wako City Japan

来源：评论

学校读者我要写书评

暂无评论

Consensus of Multiple Second-Order Agents without Velocity Measurements

Consensus of Multiple Second-Order Agents without Velocity M...

引用

2009 American control Conference (ACC 2009)

作者： Yanping Gao Long Wang Yingmin Jia Center for Systems and Control College of Engineering and Key Laboratory of Machine Perception (Ministry of Education) Peking University Beijing 100871 P. R. China Seventh Research Division Beihang University Beijing 100083 P. R. China

ISBN: (纸本)9781424445233

This paper studies consensus problems of multiple second-order agents with time-varying topology. It is assumed that each possible interaction topology is strongly connected and balanced and each agent can only obtain the measurements of its position relative to its neighbors. A feasible protocol is proposed, and by applying the linear matrix inequality technique and the common Lyapunov function approach, some sufficient conditions for consensus are established. Simulations are provided to illustrate the effectiveness of the theoretical results.

关键词： Speed measurement Agents Sufficient conditions Liapunov function Velocimetry time varying ASSAY SCALE topology simulating

来源：评论

学校读者我要写书评

暂无评论

On the controllability of Multiple Dynamic Agents with Fixed Topology

On the Controllability of Multiple Dynamic Agents with Fixed...

引用

2009 American control Conference (ACC 2009)

作者： Fangcui Jiang Long Wang Guangming Xie Zhijian Ji Yingmin Jia Center for Systems and Control College of Engineering and Key Laboratory of Machine Perception (Ministry of Education) Peking University Beijing 100871 China College of Automation Engineering Qingdao University Qingdao 266071 China The Seventh Research Division Beihang University Beijing 100083 China

ISBN: (纸本)9781424445233

This paper focuses on the controllability of multi-agent systems with fixed topology based on agreement protocols. We analyze three models of agents: single integrator, double integrator and high-order integrator. For a group of single-integrator agents, controllability is studied in a unified framework for both networks with leader-following structure and networks with undirected graph. Some new necessary/sufficient conditions for controllability of networks of single-integrator agents are established. For networks of double-integrator agents, we prove that controllability of the networks is equivalent to that of networks of single-integrator agents under the same topology and same prescribed leaders. This result is further extended to the case of networks of high-order-integrator agents. Moreover, two influencing factors of controllability of networks are investigated, that is, the selection of leaders and the link weights of graphs.

关键词： controllability Network topology Multiagent systems Protocols Communication system control control systems Distributed control Mathematical model Sufficient conditions Distributed computing

来源：评论

学校读者我要写书评

暂无评论

Robust controller Design for Networked control systems with Nonlinear Uncertainties

Robust Controller Design for Networked Control Systems with ...

引用

2009 American control Conference (ACC 2009)

作者： Junyan Yu Long Wang Mei Yu Jie Chen Yingmin Jia Intelligent Control Laboratory Center for Systems and Control College of Engineering and Key Laboratory of Machine Perception (Ministry of Education) Peking University Beijing 100871 P.R.China Department of Automation North China Electric Power University Zhuxinzhuang Dewai Beijing 102206 P.R.China Beijing Institute of Technology Key Laboratory of Complex System Intelligent Control and Decision Ministry of Education Beijing 100081 P.R.China Seventh Research Division Beihang University Beijing 100083 P.R. China

ISBN: (纸本)9781424445233

We address robust stabilization problem for networked control systems with nonlinear uncertainties and packet losses by modelling such systems as a class of uncertain switched systems. Based on theories on switched Lyapunov functions, we derive the robustly stabilizing conditions for state feedback stabilization and design packet-loss dependent controllers by solving some matrix inequalities. A numerical example and some simulations are worked out to demonstrate the effectiveness of the proposed design method.

关键词： Networked control systems robust controller design Packet loss control systems design approach Switched systems controller design State feedback Uncertainty nonlinearity

来源：评论

学校读者我要写书评

暂无评论

AAAI 2008 workshop reports

AAAI 2008 workshop reports

引用

作者： Anand, Sarabjot Singh Bunescu, Razvan Carvcdho, Vitor Chomicki, Jan Conitzer, Vincent Cox, Michael T. Dignum, Virginia Dodds, Zachary Dredze, Mark Furcy, David Gabrilovich, Evgeniy Göker, Mehmet H. Guesgen, Hans Hirsh, Haym Jannach, Dietmar Junker, Ulrich Ketter, Wolfgang Kobsa, Alfred Koenig, Sven Lau, Tessa Lewis, Lundy Matson, Eric Metzler, Ted Mihalcea, Rada Mobasher, Bamshad Pineau, Joelle Poupart, Pascal Raja, Anita Ruml, Wheeler Sadeh, Norman Shani, Guy Shapiro, Daniel Smith, Trey Taylor, Matthew E. Wagstaff, Kiri Walsh, William Zhou, Rong Department of Computer Science University of Warwick United Kingdom School of Electrical Engineering and Computer Science Ohio University United States Microsoft Live Labs United States computer science and engineering University at Buffalo United States Computer science and economics Duke University United States Intelligent Computing group of BBN Technologies Utrecht University Netherlands Department of Computer science Harvey Mudd College United States University of Pennsylvania United States University of Wisconsin United States Yahoo Research PricewaterhouseCoopers Center for Advanced Research United States Department of Computer science School of Engineering and Advanced Technology Massey University New Zealand Departent of Computer science Rutgers University United States Department of Computer Science Dortmund University of Technology. Germany ILOG Rotterdam School of Management Erasmus University Netherlands Donald Bren School of Information and Computer Sciences University of California Irvine United States Depatrment of Computer science University of Southern California United States IBM Almaden Research Center United States Department of Computer Information Technology Southern New Hampshire University United States Computer and Information Technology Program College of Technology Purdue University United States Hughes Program for Religion and Science Dialogue Oklahoma City University United States Department of Computer Science and Engineering University of North Texas United States School of Computing DePaul University United States Department of Computer Science McGill University Canada School of Computer Science University of Waterloo Canada Department of Software and Information Systems University of North Carolina Charlotte United States University of New Hampshire United States Microsoft Research Institute for the Study of Learning and Expertise Applied Reactivity Inc. United States NASA Ames Research Center Carnegie Mellon University West

AAAI was pleased to present the AAAI-08 Workshop Program, held Sunday and Monday, July 13-14, in Chicago, Illinois, USA. The program included the following 15 workshops: Advancements in POMDP Solvers;AI Education Workshop Colloquium;Coordination, Organizations, Institutions, and Norms in Agent systems, Enhanced Messaging;Human Implications of Human-Robot Interaction;Intelligent Techniques for Web Personalization and Recommender systems;Metareasoning: Thinking about Thinking;Multidisciplinary Workshop on Advances in Preference Handling;Search in Artificial Intelligence and Robotics;Spatial and Temporal Reasoning;Trading Agent Design and Analysis;Transfer learning for Complex Tasks;What Went Wrong and Why: Lessons from AI research and Applications;and Wikipedia and Artificial Intelligence: An Evolving Synergy. Copyright © 2009, Association for the Advancement of Artificial Intelligence. All rights reserved.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Special Issue on Variable Structure System control — New Designs and Applications

引用

Asian Journal of control 2008年第4期5卷

作者： Prof. Jian-Xin Xu Prof. Leonid Fridman Department of Electrical and Computer Eng. National University of Singapore 4 Engineering Drive 3 Singapore 117576 Tel +65 6874-2566 Fax +65 6779-1103 Dr Jian-Xin Xu received his Bachelor degree from Zhejiang University China in 1982. He attended the University of Tokyo Japan where he received his Master's and Ph.D. degrees in 1986 and 1989 respectively. All his degrees are in Electrical Engineering. He worked for one year in the Hitachi research Laboratory Japan and for more than one year in Ohio State University U.S.A. as a Visiting Scholar. In 1991 he joined the National University of Singapore and is currently an associate professor in the Department of Electrical Engineering. His research interests lie in the fields of learning control variable structure control fuzzy logic control discontinuous signal processing and applications to motion control and process control problems. He is the associate editor of Asian Journal of Control member of TC on variable structure systems and sliding mode control of IEEE Control Systems Society and a senior member of IEEE. He has produced more than 90 peer-refereed journal papers near 160 technical papers in conference proceedings and authored/edited 4 books. Division de Estudios de Posgrado Facultad de Ingenieria National Autonomous University of Mexico DEP-FI UNAM Edificio “A” Circuito Exterior Ciudad Universitaria A. P. 70–256 C.P.04510 Mexico D.F. Mexico Tel +52 55 56223014 Fax +52 55 56161719 Dr. Leonid M. Fridman received his M.S in mathematics from Kuibyshev (Samara) State University Russia Ph.D. in Applied Mathematics from Institute of Control Science (Moscow) and Dr. of Science degrees in Control Science from Moscow State University of Mathematics and Electronics in 1976 1988 and 1998 respectively. In 1976–1999 Dr. Fridman was with the Department of Mathematics at the Samara State Architecture and Civil Engineering Academy Samara Russia. In 2000–2002 he was with the Department of Postgraduate Study and Investigations at the Chihuahu

来源：评论

学校读者我要写书评

暂无评论

A Study On Iterative learning control With Adjustment Of learning Interval For Monotone Convergence In The Sense Of Sup-Norm

引用

Asian Journal of control 2008年第1期4卷

作者： Kwang-Hyun Park Zeungnam Bien Division of EE Department of EECS Korea Advanced Institute of Science and Technology 373–1 Kusong-dong Yusong-gu Taejon 305–701 Korea. Zeungname Bien:received the B.S. degree in electronics engineering from Seoul National University Seoul Korea in 1969 and the M.S. and Ph.D. degrees in electrical engineering from the University of Iowa Iowa City Iowa U.S.A. in 1972 and 1975 respectively. During 1976–1977 academic years he taught as assistant professor at the Department of Electrical Engineering University of Iowa. Then Dr. Bien joined Korea Advanced Institute of Science and Technology summer 1977 and is now Professor of Control Engineering at the Department of Electrical Engineering and Computer Science KAIST. Dr. Bien was the president of the Korea Fuzzy Logic and Intelligent Systems Society during 1990–1995 and also the general chair of IFSA World Congress 1993 and for FUZZ-IEEE99 respectively. He is currently co-Editor-in-Chief for International Journal of Fuzzy Systems (IJFS) Associate Editor for IEEE Transactions on Fuzzy Systems and a regional editor for the International Journal of Intelligent Automation and Soft Computing. He has been serving as Vice President for IFSA since 1997 and is now Chief Chairman of Institute of Electronics Engineers of Korea and Director of Humanfriendly Welfare Robot System Research Center. His current research interests include intelligent control methods with emphasis on fuzzy logic systems service robotics and rehabilitation engineering and large-scale industrial control systems. Kwang-Hyun Park:received the B.S. M.S. and Ph.D. degrees in electrical engineering and computer science from KAIST Korea in 1994 19997 and 2001 respectively. He is now a researcher at Human-friendly Welfare Robot System Research Center. His research interests include learning control machine learning human-friendly interfaces and service robotics.

It has been found that some huge overshoot in the sense of sup-norm may be observed when typical iterative learning control (ILC) algorithms are applied to LTI systems, even though monotone convergence in the sense of λ-norm is guaranteed. In this paper, a new ILC algorithm with adjustment of learning interval is proposed to resolve such an undesirable phenomenon, and it is shown that the output error can be monotonically converged to zero in the sense of sup-norm when the proposed ILC algorithm is applied. A numerical example is given to show the effectiveness of the proposed algorithm.

关键词： Iterative learning control monotone convergence learning interval sup-norm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：